zoukankan      html  css  js  c++  java
  • tflearn数据预处理

    #I just added a function for custom data preprocessing, you can use it as:
    
    minmax_scaler = sklearn.preprocessing.MinMaxScaler(....)
    
    def my_func(X):
        X = minmax_scaler.inverse_transform(X)
        return X
    
    dprep = tflearn.DataPreprocessing()
    dprep.add_custom_preprocessing(my_func)
    
    input_layer = tflearn.input_data(shape=[...], data_preprocessing=dprep)
    

    我自己的应用:

    def my_func(X):
        X = X/255.
        return X
    
    def get_model(width, height, classes=40):
        # TODO, modify model
        # Real-time data preprocessing
        img_prep = tflearn.ImagePreprocessing()
        #img_prep.add_featurewise_zero_center(per_channel=True)
        #img_prep.add_featurewise_stdnorm()
    
        img_prep.add_custom_preprocessing(my_func)
    
        network = input_data(shape=[None, width, height, 1], data_preprocessing=img_prep)  # if RGB, 224,224,3
        #network = input_data(shape=[None, width, height, 1])
        network = conv_2d(network, 32, 3, activation='relu')
        network = max_pool_2d(network, 2)
        network = conv_2d(network, 64, 3, activation='relu')
        network = conv_2d(network, 64, 3, activation='relu')
        network = max_pool_2d(network, 2)
        network = fully_connected(network, 512, activation='relu')
        network = dropout(network, 0.5)
        network = fully_connected(network, classes, activation='softmax')
        network = regression(network, optimizer='adam',
                             loss='categorical_crossentropy',
                             learning_rate=0.001)
        model = tflearn.DNN(network, tensorboard_verbose=0)
        return model
    
  • 相关阅读:
    补:冲刺Day1
    需求规格说明书2.0
    补:冲刺Day2
    冲刺Day3
    Base64上传图片
    C#怎样通过url调用接口
    js键盘控制DIV移动
    利用MVC的过滤器实现url的参数加密和解密
    在.net MVC中异步上传图片或者文件
    mvc url路由参数的加密和解密
  • 原文地址:https://www.cnblogs.com/bonelee/p/8980939.html
Copyright © 2011-2022 走看看